ceph: do not touch_caps while iterating over caps list

Avoid confusing iterate_session_caps(), flag the session while we are
iterating so that __touch_cap does not rearrange items on the list.

All other modifiers of session->s_caps do so under the protection of
s_mutex.

Signed-off-by: Sage Weil <sage@newdream.net>

3 files changed, 19 insertions, 7 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index dfb509f53542..93c1afe3f0b3 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -697,10 +697,15 @@ static void __touch_cap(struct ceph_cap *cap)
 {
         struct ceph_mds_session *s = cap->session;
 
-        dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap,
-             s->s_mds);
         spin_lock(&s->s_cap_lock);
-        list_move_tail(&cap->session_caps, &s->s_caps);
+        if (!s->s_iterating_caps) {
+                dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap,
+                     s->s_mds);
+                list_move_tail(&cap->session_caps, &s->s_caps);
+        } else {
+                dout("__touch_cap %p cap %p mds%d NOP, iterating over caps\n",
+                     &cap->ci->vfs_inode, cap, s->s_mds);
+        }
         spin_unlock(&s->s_cap_lock);
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d7cecc3366da..63ca3b1ad45f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -337,10 +337,12 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
         s->s_renew_seq = 0;
         INIT_LIST_HEAD(&s->s_caps);
         s->s_nr_caps = 0;
+        s->s_trim_caps = 0;
         atomic_set(&s->s_ref, 1);
         INIT_LIST_HEAD(&s->s_waiting);
         INIT_LIST_HEAD(&s->s_unsafe);
         s->s_num_cap_releases = 0;
+        s->s_iterating_caps = false;
         INIT_LIST_HEAD(&s->s_cap_releases);
         INIT_LIST_HEAD(&s->s_cap_releases_done);
         INIT_LIST_HEAD(&s->s_cap_flushing);
@@ -699,6 +701,7 @@ static int iterate_session_caps(struct ceph_mds_session *session,
 
         dout("iterate_session_caps %p mds%d\n", session, session->s_mds);
         spin_lock(&session->s_cap_lock);
+        session->s_iterating_caps = true;
         list_for_each_entry_safe(cap, ncap, &session->s_caps, session_caps) {
                 inode = igrab(&cap->ci->vfs_inode);
                 if (!inode)
@@ -706,13 +709,15 @@ static int iterate_session_caps(struct ceph_mds_session *session,
                 spin_unlock(&session->s_cap_lock);
                 ret = cb(inode, cap, arg);
                 iput(inode);
-                if (ret < 0)
-                        return ret;
                 spin_lock(&session->s_cap_lock);
+                if (ret < 0)
+                        goto out;
         }
+        ret = 0;
+out:
+        session->s_iterating_caps = false;
         spin_unlock(&session->s_cap_lock);
-
-        return 0;
+        return ret;
 }
 
 static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
@@ -935,6 +940,7 @@ static int trim_caps(struct ceph_mds_client *mdsc,
                 dout("trim_caps mds%d done: %d / %d, trimmed %d\n",
                      session->s_mds, session->s_nr_caps, max_caps,
                         trim_caps - session->s_trim_caps);
+                session->s_trim_caps = 0;
         }
         return 0;
 }
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 41af5ca316e6..b1c2025227c5 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -114,6 +114,7 @@ struct ceph_mds_session {
         int               s_num_cap_releases;
         struct list_head  s_cap_releases; /* waiting cap_release messages */
         struct list_head  s_cap_releases_done; /* ready to send */
+        bool              s_iterating_caps;
 
         /* protected by mutex */
         struct list_head  s_cap_flushing;     /* inodes w/ flushing caps */